首页> 外文会议>International Conference on Mathematics and Computers in Sciences and Industry >Description and Recognition of Symmetrical and Freely Oriented Images Based on Parallel Shift Technology
【24h】

Description and Recognition of Symmetrical and Freely Oriented Images Based on Parallel Shift Technology

机译:基于并行换档技术的对称和自由定向图像的描述和识别

获取原文

摘要

The method of description and recognition of images based on the technology of parallel shift is described. The parallel shift technology allows to form only one characteristic for describing of images. This feature is the area of the image, which is determined by the number of cells belonging to the image. The main characteristics of the complex image area are described. The problem of using parallel shift technology is the inability to recognize symmetrical images and images with free orientation. In accordance with the problem in the paper a method is described that allows to recognize the orientation of the image, as well as recognize symmetrical images that have the same functions of area of intersection. To solve the problem, additional elements are introduced on one of the edges of the image, which in a small amount distinguish it from the original image, and additional quantitative characteristics of the area are introduced. The additional elements are introduced only on one of the edges of the image for all images at the system input. For each rotated and symmetrical image with equal functions, the intersection areas a new intersection functions are defined. Differences in the functions of the areas of intersection of both images are determined and on the based on the obtained quantitative characteristics of the function of the area of intersection of the images the shape of the image are determined. To form the intersection function of the areas of the modified image, the number of shifts is increased by one, and also the function change occurs at each step in accordance with the introduced additional elements. The conducted research showed high reliability of image recognition.
机译:描述了基于并行移位技术的图像描述和识别方法。并行移位技术允许仅形成用于描述图像的一个特征。该特征是图像的区域,由属于图像的单元数确定。描述了复杂图像区域的主要特征。使用并行移位技术的问题是无法识别具有自由方向的对称图像和图像。根据本文中的问题,描述了一种方法,其允许识别图像的方向,以及识别具有相同交叉区域功能的对称图像。为了解决问题,在图像的一个边缘上引入附加元件,其在少量将其区分开地区分,并且引入了该区域的额外定量特性。附加元件仅在系统输入的所有图像的图像的一个边缘上引入。对于具有相同功能的每个旋转和对称图像,交叉区域定义了新的交叉功能。确定两个图像的交叉区域的功能的差异,并且基于基于所获得的图像的函数的定量特性,确定图像的形状的图像的形状。为了形成修改图像的区域的交叉点函数,换档的数量增加一个,并且根据引入的附加元件,在每个步骤中发生函数变化。进行的研究表明了图像识别的高可靠性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号